{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RWNVR5J2VS7JVERRK23I4MCFEU","short_pith_number":"pith:RWNVR5J2","canonical_record":{"source":{"id":"2509.09722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9","abstract_canon_sha256":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5"},"schema_version":"1.0"},"canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","source":{"kind":"arxiv","id":"2509.09722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09722v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"RWNVR5J2VS7J","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"RWNVR5J2VS7JVERR","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"RWNVR5J2","created_at":"2026-07-05T12:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RWNVR5J2VS7JVERRK23I4MCFEU","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9","abstract_canon_sha256":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5"},"schema_version":"1.0"},"canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.864120Z","signature_b64":"vw/Ftd0B0yXLwt6ZxWwVeAYQ0IWnJZDzL+2J7toXuqQaMPUIxpFx4aAb3jK6JN0sGNFbJNj5VZKa4xXAnM7lAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","last_reissued_at":"2026-07-05T12:09:47.863537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.863537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09722","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"du5CpkNeJlym00PwD+TvErjXlueREcY49N3vPobPrx8O9DHqLxcmzOvffYaTbDVmFjEG7GMYB5HK/phr3m/6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:29:42.466826Z"},"content_sha256":"6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941","schema_version":"1.0","event_id":"sha256:6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RWNVR5J2VS7JVERRK23I4MCFEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving MLLM Historical Record Extraction with Test-Time Image","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Taylor Archibald, Tony Martinez","submitted_at":"2025-09-10T03:18:24Z","abstract_excerpt":"We present a novel ensemble framework that stabilizes LLM based text extraction from noisy historical documents. We transcribe multiple augmented variants of each image with Gemini 2.0 Flash and fuse these outputs with a custom Needleman Wunsch style aligner that yields both a consensus transcription and a confidence score. We present a new dataset of 622 Pennsylvania death records, and demonstrate our method improves transcription accuracy by 4 percentage points relative to a single shot baseline. We find that padding and blurring are the most useful for improving accuracy, while grid warp pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09722","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.09722/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eojuA3Bt0XtgoI8l57FhPSeVVM+hiEfj8DLDP4kDJQcASgTixymDUN1bEUqOjDm8QQX93PNTzpGQCAPIb4KGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:29:42.467353Z"},"content_sha256":"88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b","schema_version":"1.0","event_id":"sha256:88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RWNVR5J2VS7JVERRK23I4MCFEU/bundle.json","state_url":"https://pith.science/pith/RWNVR5J2VS7JVERRK23I4MCFEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RWNVR5J2VS7JVERRK23I4MCFEU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T10:29:42Z","links":{"resolver":"https://pith.science/pith/RWNVR5J2VS7JVERRK23I4MCFEU","bundle":"https://pith.science/pith/RWNVR5J2VS7JVERRK23I4MCFEU/bundle.json","state":"https://pith.science/pith/RWNVR5J2VS7JVERRK23I4MCFEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RWNVR5J2VS7JVERRK23I4MCFEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RWNVR5J2VS7JVERRK23I4MCFEU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9"},"schema_version":"1.0","source":{"id":"2509.09722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09722v1","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09722","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"RWNVR5J2VS7J","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"RWNVR5J2VS7JVERR","created_at":"2026-07-05T12:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"RWNVR5J2","created_at":"2026-07-05T12:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b","target":"graph","created_at":"2026-07-05T12:09:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.09722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel ensemble framework that stabilizes LLM based text extraction from noisy historical documents. We transcribe multiple augmented variants of each image with Gemini 2.0 Flash and fuse these outputs with a custom Needleman Wunsch style aligner that yields both a consensus transcription and a confidence score. We present a new dataset of 622 Pennsylvania death records, and demonstrate our method improves transcription accuracy by 4 percentage points relative to a single shot baseline. We find that padding and blurring are the most useful for improving accuracy, while grid warp pe","authors_text":"Taylor Archibald, Tony Martinez","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title":"Improving MLLM Historical Record Extraction with Test-Time Image"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09722","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941","target":"record","created_at":"2026-07-05T12:09:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"40a392ae1b825592e5fcd3ec741df0a8d790569f971b6cdb16d53cfdec8c1ce5","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-10T03:18:24Z","title_canon_sha256":"8c604625c02d7f0a9ea8b4cd84fe0ee7d937f5c9b8890c98bead22c0b560cdc9"},"schema_version":"1.0","source":{"id":"2509.09722","kind":"arxiv","version":1}},"canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d9b58f53aacbe9a923156b68e3045251acfaec336ca61a160defabb5c22bad6","first_computed_at":"2026-07-05T12:09:47.863537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:47.863537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vw/Ftd0B0yXLwt6ZxWwVeAYQ0IWnJZDzL+2J7toXuqQaMPUIxpFx4aAb3jK6JN0sGNFbJNj5VZKa4xXAnM7lAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:47.864120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c0b6f11b8550887917553e216f40cec0a515385606f63c7e9c085fb202b6941","sha256:88ca6f60114d4905aeb0ed0c9e8acaad2ad0ae61204040e90d20542e8ba0ed0b"],"state_sha256":"39ed690198c796bc3db7ab25c3b2a4a58315e2830ad5a99239eb1f38d4b1a334"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zzl0FKaRw+YitPnf3Onm0/PEzdLlqQk0ED/Pf6UlmWVWwDt4W2V52PtJqy7jpIkp9GK0ijUbXfVY7K/ieEpABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:29:42.470833Z","bundle_sha256":"d18bdd262b6c633ef4a50bd99dc2f78eda5d40ee0e8768fbbc3a78bc5c0b56a9"}}